top of page
Epistemic Active Inference for Controlled Emergence (EAI-CE)
Nicola Bezzo (UVA PI), Insup Lee (UPenn Co-PI), Oleg Sokolsky (UPenn Co-PI),
Linh Phan (Upenn Co-PI), Fanxin Kong (ND Co-PI)
This project seeks fundamentally new approaches for enabling large-scale decentralized AI collectives to operate effectively under partial observability, uncertain information, limited communication, and evolving mission objectives.
This page contains links to repositories with demonstrations and codes of prior related work to the proposed effort:
J. Reasoner, L. Bramblett, and N. Bezzo
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025.
Demos + Code for "Robust Online Epistemic Replanning of Multi-Robot Missions”
L. Bramblett, B. Miloradović, P. Sherman, A.V. Papadopoulos, and N. Bezzo,
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
Demos + Code for "Higher Order Reasoning for Collaborative Communicationless Mobile Robot Operations”
J. Reasoner, and N. Bezzo,
IEEE/RSJ International Conference on Robotics and Automation (ICRA), 2026
Demos for "Detection of Nonrandom Sign-based Behavior for Resilient Coordination of Robotic Swarms”
P.J. Bonczek, R. Peddi, S. Gao, and N. Bezzo
IEEE Transactions on Robotics, 2022.
F. Kong
bottom of page